Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mathematical Reasoning on GSM8K v1 (test)

95.1Accuracy

Pass@k

55.47665.76376.0586.337Jul 15, 2024Nov 6, 2024Feb 28, 2025Jun 23, 2025Oct 15, 2025Feb 6, 2026Jun 1, 2026
Updated 22h ago

Evaluation Results

MethodLinks
2026.06
95.1--
2026.06
95.1--
2026.06
95.1--
2026.06
95.1--
2025.09
94.9--
2026.06
94.8--
2026.06
94.8--
2026.06
94.8--
2025.09
94.22--
2026.01
9324.19-
2026.01
92.7727.341.13
2026.06
92.7--
2026.01
92.6927.211.12
2026.01
92.5429.551.22
2026.06
92.5--
2026.06
92.3--
2026.01
92.0930.981.28
2026.01
91.9430.11.24
2026.01
91.8831.491.3
2026.01
91.2833.211.37
2026.01
91.0832.571.35
2026.06
90.4--
2026.01
90.2735.11.45
2026.01
89.9635.071.45
2026.06
89.3--
2026.06
89.2--
2026.06
88.6--
2026.06
87.6--
2025.03
87.1--
2026.06
86.8--
2025.03
86.1--
2026.06
86--
2025.09
85.98--
2024.07
85.7--
2026.06
85.7--
2026.06
85.4--
2025.03
85.1--
2025.03
85.1--
2025.03
84.9--
2024.07
84.8--
2025.03
84.8--
2025.03
84.6--
2026.05
84.31--
2026.06
83.9--
2025.03
83.4--
2026.01
82.7739.581.03
2026.01
82.539.111.02
2026.01
82.538.4-
2026.05
81.95--
2026.05
81.81--
2026.05
81.73--
2026.05
81.41--
2026.06
81.2--
2026.01
81.0748.351.26
2026.06
81--
2026.01
80.9645.351.18
2026.06
80.7--
2026.06
80.5--
2026.01
80.2945.061.17
2026.05
80.12--
2026.06
80.1--
2026.06
79.7--
2024.07
79.6--
2024.07
79.6--
2026.06
79.6--
2026.01
79.4650.961.33
2026.01
79.3947.121.23
2026.06
79.3--
2026.06
79.1--
2026.06
78.7--
2026.01
78.448.871.27
2026.06
78--
2026.06
77.7--
2026.06
77.3--
2026.06
77.3--
2026.01
77.1361.451.6
2026.01
75.5953.71.4
2026.06
75.2--
2026.06
75--
2026.06
74.8--
2026.06
74--
2026.06
73.4--
2025.09
72.31--
2026.06
71.8--
2026.06
71.3--
2026.06
70.5--
2026.06
69.8--
2026.06
69.7--
2026.06
67.9--
2026.06
67.5--
2026.06
65.4--
2026.06
65.1--
2026.06
62.7--
2024.07
60.3--
2026.06
60.2--
2026.06
59.2--
2026.06
59.1--
2026.06
58.5--
2026.06
57.2--
2026.06
57--
Showing 100 of 118 rows